Issue Station
Sign In
Tools hereToolbox

hermes - 💡(How to fix) Fix [Bug]: WhatsApp gateway should support intentional no-reply/no-op responses and must not send provider diagnostic spam when the correct response is silence

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Error Message

Operating System

MacOS 15.7.7

Python Version

No response

Hermes Version

Hermes Agent v0.14.0 (2026.5.16) Project: /Users/den/.hermes/hermes-agent Python: 3.11.15 OpenAI SDK: 2.24.0

Additional Logs / Traceback (optional)

Root Cause

Root Cause Analysis (optional)

Code Example

User:
So this is just a fun message nothing for anyone to reply to. If you reply, you are doing it wrong.

User:
@Hermes Assistant do not reply to this either

### Expected Behavior

No response at all. 

Something in logs would be appropriate, or even a message to the home channel but not in the group/chat where a response is inappropriate.

### Actual Behavior

Hermes Assistant:
⚠ Configured auxiliary compression provider 'openrouter' is unavailable — context compression will drop middle turns without a summary. Check auxiliary.compression in config.yaml and reauthenticate that provider.

Hermes Assistant:
⚠️ Empty response from model — retrying (1/3)

Hermes Assistant:
⚠️ Empty response from model — retrying (2/3)

Hermes Assistant:
⚠️ Empty response from model — retrying (3/3)

Hermes Assistant:
⚠️ Model returning empty responses — switching to fallback provider...

Hermes Assistant:
❌ Model returned no content after all retries and fallback attempts.

Hermes Assistant:
⚠️ The model returned no response after processing tool results. This can happen with some models — try again or rephrase your question.

### Affected Component

Gateway (Telegram/Discord/Slack/WhatsApp)

### Messaging Platform (if gateway-related)

WhatsApp

### Debug Report

---

### Operating System

MacOS 15.7.7

### Python Version

_No response_

### Hermes Version

Hermes Agent v0.14.0 (2026.5.16) Project: /Users/den/.hermes/hermes-agent Python: 3.11.15 OpenAI SDK: 2.24.0

### Additional Logs / Traceback (optional)

---

### Root Cause Analysis (optional)

_No response_

### Proposed Fix (optional)

Treat empty final assistant content as silent success when:

1. the model did not call tools requiring user-visible output
2. the last user message explicitly requests no reply
3. a platform policy/skill marks the turn as no-op
4. a gateway-level allow_silent_response setting is enabled

config example:
RAW_BUFFERClick to expand / collapse

Bug Description

Hermes currently appears to assume that every processed WhatsApp turn must produce an outbound WhatsApp message. This is wrong for real group-chat usage.

Sometimes the correct assistant behavior is to process the message and send no response. For example, the user may explicitly say “do not reply,” or the agent may decide that a message does not require a response.

In my test, I explicitly told the assistant not to reply, but the WhatsApp gateway still sent multiple diagnostic/error messages into the group after the model produced no useful final content.

This creates socially awkward group-chat behavior and makes Hermes noisy in production WhatsApp groups.

Steps to Reproduce

Platform: WhatsApp gateway / group chat

Config intent:

  • whatsapp.require_mention: true
  • no free-response group
  • WhatsApp tool progress disabled via display.platforms.whatsapp.tool_progress: 'off'

Test messages:

User:
So this is just a fun message nothing for anyone to reply to. If you reply, you are doing it wrong.

User:
@Hermes Assistant do not reply to this either

### Expected Behavior

No response at all. 

Something in logs would be appropriate, or even a message to the home channel but not in the group/chat where a response is inappropriate.

### Actual Behavior

Hermes Assistant:
⚠ Configured auxiliary compression provider 'openrouter' is unavailable — context compression will drop middle turns without a summary. Check auxiliary.compression in config.yaml and reauthenticate that provider.

Hermes Assistant:
⚠️ Empty response from model — retrying (1/3)

Hermes Assistant:
⚠️ Empty response from model — retrying (2/3)

Hermes Assistant:
⚠️ Empty response from model — retrying (3/3)

Hermes Assistant:
⚠️ Model returning empty responses — switching to fallback provider...

Hermes Assistant:
❌ Model returned no content after all retries and fallback attempts.

Hermes Assistant:
⚠️ The model returned no response after processing tool results. This can happen with some models — try again or rephrase your question.

### Affected Component

Gateway (Telegram/Discord/Slack/WhatsApp)

### Messaging Platform (if gateway-related)

WhatsApp

### Debug Report

```shell
Debug report uploaded:
  Report       https://paste.rs/fOsmx
  agent.log    https://paste.rs/kypPH
  gateway.log  https://paste.rs/y4oX2

Operating System

MacOS 15.7.7

Python Version

No response

Hermes Version

Hermes Agent v0.14.0 (2026.5.16) Project: /Users/den/.hermes/hermes-agent Python: 3.11.15 OpenAI SDK: 2.24.0

Additional Logs / Traceback (optional)

Root Cause Analysis (optional)

No response

Proposed Fix (optional)

Treat empty final assistant content as silent success when:

  1. the model did not call tools requiring user-visible output
  2. the last user message explicitly requests no reply
  3. a platform policy/skill marks the turn as no-op
  4. a gateway-level allow_silent_response setting is enabled

config example:

gateway:
  allow_silent_response: true
  suppress_provider_diagnostics_in_chat: true

whatsapp:
  allow_silent_response: true
  suppress_diagnostics: true

Are you willing to submit a PR for this?

  • I'd like to fix this myself and submit a PR

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#memory optimization#batch processing#GPU compatibility#latency issue#model loading

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

hermes - 💡(How to fix) Fix [Bug]: WhatsApp gateway should support intentional no-reply/no-op responses and must not send provider diagnostic spam when the correct response is silence